conftrace_

alignment technique

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

influenceable reward (1) critical reasoning (1) dynamic preference (1) explicit bia (1) large language model (1) multiple choice evaluation (1) social bia (1) optimization horizon (1) robustness evaluation (1) implicit bia (1)

Papers

Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection ACL 2025 Wait, that’s not an option: LLMs Robustness with Incorrect Multiple-Choice Options ACL 2025 AI Alignment with Changing and Influenceable Reward Functions ICML 2024